Token-Domain Multiple Access: Exploiting Semantic Orthogonality for Collision Mitigation

2025-02-10

AI Summary

To address semantic transmission failure caused by token collisions among massive IoT devices sharing a common tokenizer and modulation codebook, this paper proposes Token-Domain Multiple Access (ToDMA), a semantic-level multiple access mechanism. ToDMA pioneers the integration of semantic orthogonality into MAC design—departing from conventional physical-layer orthogonality constraints—and leverages context awareness and cross-device semantic orthogonality to enable token collision detection, source attribution, and semantic-level conflict resolution at the receiver. Technically, it synergizes Transformer-based semantic tokenization, a shared tokenizer, codebook-driven token modulation, and context-guided multi-source decoupled reconstruction. Evaluated on image transmission tasks, ToDMA reduces end-to-end latency significantly and improves PSNR by 3.2 dB and SSIM by 0.08 over orthogonal and non-orthogonal baselines, empirically validating the feasibility and superiority of semantic-domain multiple access.

Technology Category

• Application Domains: Internet of Things, Sensor Networks & Smart Cities
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Multi-modal Vision

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

Token communications is an emerging generative semantic communication concept that reduces transmission rates by using context and transformer-based token processing, with tokens serving as universal semantic units. In this paper, we propose a semantic multiple access scheme in the token domain, referred to as ToDMA, where a large number of devices share a tokenizer and a modulation codebook for source and channel coding, respectively. Specifically, the source signal is tokenized into sequences, with each token modulated into a codeword. Codewords from multiple devices are transmitted simultaneously, resulting in overlap at the receiver. The receiver detects the transmitted tokens, assigns them to their respective sources, and mitigates token collisions by leveraging context and semantic orthogonality across the devices' messages. Simulations demonstrate that the proposed ToDMA framework outperforms context-unaware orthogonal and non-orthogonal communication methods in image transmission tasks, achieving lower latency and better image quality.

Problem

• Mitigating token collisions
• Enhancing semantic communication
• Improving image transmission efficiency

Innovation

• Token-Domain Multiple Access
• Semantic Orthogonality Exploitation
• Transformer-Based Token Processing